postprocess_results.py 文件源码

def reorderClusters(B, X, GDM, returnOrderIndices = False):
    Bloc = np.array(B)
    Xloc = ds.listofarrays2arrayofarrays(X)

    Bloc = Bloc[:, np.any(Bloc, axis=0)]  # Only keep non-empty clusters

    B_ordered = np.zeros(Bloc.shape, dtype=bool)
    K = Bloc.shape[1]  # Number of clusters
    L = Xloc.shape[0]  # Number of datasets

    if K == 0:
        return Bloc

    # Find Cmeans and distances between clusters
    Cmeans = np.array([None] * L, dtype=object)
    D = np.zeros([K, K, L])  # KxKxL
    for l in range(L):
        Cmeans[l] = np.zeros([K, Xloc[l].shape[1]], dtype=float)  # (K) x (X[l] samples)
        for k in range(K):
            Cmeans[l][k] = np.mean(Xloc[l][Bloc[GDM[:, l], k], :], axis=0)
        D[:, :, l] = skdists.euclidean_distances(Cmeans[l])  # KxK
    D = np.median(D, axis=2)  # KxK

    # Set first cluster as first, then find closest by closest
    B_ordered[:, 0] = Bloc[:, 0]
    I = np.zeros(K, dtype=int)
    I[0] = 0
    clustersDone = np.zeros(K, dtype=bool)
    clustersDone[0] = True
    for k in range(1,K):
        relevantD = D[I[k-1], ~clustersDone]
        clustersLeft = np.nonzero(~clustersDone)[0]
        nextCluster = np.argmin(relevantD)
        nextCluster = clustersLeft[nextCluster]
        B_ordered[:, k] = Bloc[:, nextCluster]
        I[k] = nextCluster
        clustersDone[nextCluster] = True

    if returnOrderIndices:
        return (B_ordered, I)
    else:
        return B_ordered